arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2011.12221eess.AS
收藏

用于语音到意图应用的光转换器Transformer

A light transformer for speech-to-intent applications

Pu Wang, Hugo Van hamme

摘要:

口语理解(SLU)系统可以使生活更舒适,更安全(例如在汽车中),或者可以增加身体残疾用户的独立性。然而,由于语音的变化来源很多,一个训练有素的系统很难转移到其他条件,如不同的语言或语音障碍的用户。补救措施是设计一个用户自教的SLU系统,可以从用户的演示中从头开始完全学习,这反过来又要求系统的模型在只需几个训练样本后就迅速收敛。在本文中,我们提出了一个轻的Transformer结构,通过使用一个简化的相对位置编码的目标,以减少模型的大小和提高效率。光Transformer可作为现有用户示教多任务SLU系统的替代语音编码器。在三个具有挑战性语音条件的数据集上的实验结果表明,该方法的性能优于现有系统和其他最先进的模型,其模型大小和训练时间仅为原始模型的一半。

英文摘要:

Spoken language understanding (SLU) systems can make life more agreeable, safer (e.g. in a car) or can increase the independence of physically challenged users. However, due to the many sources of variation in speech, a well-trained system is hard to transfer to other conditions like a different language or to speech impaired users. A remedy is to design a user-taught SLU system that can learn fully from scratch from users' demonstrations, which in turn requires that the system's model quickly converges after only a few training samples. In this paper, we propose a light transformer structure by using a simplified relative position encoding with the goal to reduce the model size and improve efficiency. The light transformer works as an alternative speech encoder for an existing user-taught multitask SLU system. Experimental results on three datasets with challenging speech conditions prove our approach outperforms the existed system and other state-of-art models with half of the original model size and training time.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑